Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    interactions and conflicts related to personal relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    +#+#
    -0.78
     iſt
    -0.76
    ContentAsync
    -0.73
     становника
    -0.71
     venons
    -0.69
    -0.66
     AppColors
    -0.65
    Hozzáférés
    -0.62
     Wav
    -0.62
    adaptiveStyles
    -0.62
    POSITIVE LOGITS
     revela
    0.49
     reveals
    0.48
    ляє
    0.46
     gets
    0.45
    bw
    0.45
     revealing
    0.43
    ">—
    0.43
     un
    0.42
     revealed
    0.42
     te
    0.42
    Act Density 0.360%

    No Known Activations